arXiv:2410. 06814v2 Announce Type: replace Abstract: Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model.
By Hengxiang Zhang, Qiang Hu, Hongxin Wei
The paper investigates whether inexpensive spectral metrics from the heavy‑tailed self‑regularisation framework can predict membership inference attack (MIA) vulnerability, offering a scalable alternative to costly shadow‑model attacks. Experiments on image and tabular classification tasks show that stable rank correlates positively with overall MIA success, while Log alpha‑Norm correlates negatively with MIA risk in low false‑positive regimes, outperforming conventional generalisation gap measures. These findings suggest that neural network spectra contain privacy leakage signals not captured by traditional overfitting metrics, pointing to spectral analysis as a promising direction for privacy auditing.
By Richard J. Preen, Jim Smith
arXiv:2602. 02819v4 Announce Type: replace Abstract: Membership Inference Attacks (MIAs) aim to distinguish training points (members) from unseen data (non-members), and are widely used to quantify memorization and assess privacy risks.
By Mathieu Even, Cl\'ement Berenfeld, Linus Bleistein, Tudor Cebere, Julie Josse, Aur\'elien Bellet
The paper introduces a new privacy vulnerability in diffusion language models (DLMs) called token‑level memorization asymmetry, derived from theoretical analysis of diffusion training dynamics. It proposes Q‑Skew, a quantile‑weighted skewness indicator, to perform membership inference on fine‑tuned DLMs, outperforming existing baselines across multiple datasets and models. Additionally, Q‑Skew can be used to extract personally identifiable information (PII), demonstrating a broader privacy attack surface.
By Shengfang Zhai, Leo Marchyok, Yuling Shi, Huanran Chen, Yinpeng Dong, Jiaheng Zhang, Sanghyun Hong
The paper "Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses" provides a comprehensive review of model inversion (MI) attacks that exploit trained deep neural networks to reconstruct private training data. It traces the evolution of MI from early machine‑learning contexts to recent DNN‑based attacks across various modalities and learning tasks, offering a detailed taxonomy and comparative analysis of both attacks and defenses. The authors also present an open‑source toolbox on GitHub to support further research in this area.
By Hao Fang, Yixiang Qiu, Hongyao Yu, Wenbo Yu, Jiawei Kong, Baoli Chong, Bin Chen, Xuan Wang, Shu-Tao Xia, Ke Xu
arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.
By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz